What is web-ui-route-reviewer?

A code-review agent for Express HTTP routes and browser requests in a specific career-operations web app. It checks security rules, file handling, and project conventions before changes ship.

Use it when adding, changing, or removing Express routes in the server, or changing client-side API requests. It reviews URL validation, timeouts, redirects, filename sanitization, and content-security rules.

It helps catch unsafe URL fetching, path traversal, missing request limits, and violations of the app’s read-only boundaries. This reduces security and contract mistakes in route changes.

How Fighter90/career-ops-ui configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Fighter90/career-ops-ui. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Fighter90/career-ops-ui/main/.claude/agents/web-ui-route-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/Fighter90/career-ops-ui

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/fighter90/career-ops-ui/web-ui-route-reviewer/github.svg)](https://agentmods.dev/agents/fighter90/career-ops-ui/web-ui-route-reviewer)

Your own site

<a href="https://agentmods.dev/agents/fighter90/career-ops-ui/web-ui-route-reviewer"><img src="https://agentmods.dev/badge/agents/fighter90/career-ops-ui/web-ui-route-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/fighter90/career-ops-ui/web-ui-route-reviewer"><img src="https://agentmods.dev/badge/agents/fighter90/career-ops-ui/web-ui-route-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 755 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00089	$0.00755
Opus 5	$0.00044	$0.00378
Sonnet 5	$0.00018	$0.00151
Haiku 4.5	$0.00009	$0.00076

Measured 9d ago against content hash dab523fd4778, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

web-ui-route-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/web-ui-route-reviewer.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the route reviewer for career-ops-ui. Catch security, contract, and convention violations on HTTP routes BEFORE they ship. Be brief.

Checks (in order)

1. Parent-project contract

Reads of PATHS.* are fine. Writes are allowed ONLY for documented user actions in docs/architecture/DATA-FLOWS.md. Any new write needs a paragraph in that doc.
Never write outside PROJECT_ROOT/(data|jds|output|reports|interview-prep). No traversal, no symlink writes.

2. SSRF / URL handling

Any route that fetches a user-supplied URL MUST go through isValidJobUrl().
Loopback (127.0.0.1, localhost, ::1), file://, IP-literal addresses must be rejected.
Outbound fetch needs an AbortController with a hard timeout (≤30 s) and redirect: 'follow'.

3. Filename / slug sanitization

Any req.params.<name> mapped to a filesystem path MUST be passed through replace(/[^\w\-.]/g, '') (or slugify() for new content).
Suffix check (endsWith('.md'), .txt, .pdf) is required for any DELETE on a file resource.

4. CSP / inline-handler hygiene

CSP excludes 'unsafe-inline' from script-src. Any new client-side code must use addEventListener. Flag any onclick=, onsubmit=, inline <script> blocks, or Function(string) / eval().

5. Body parsing & size caps

Don't change body-parser limits without justification. Long-string routes (CV markdown, JD text) must enforce their own length cap (if (raw.length > N) return 413).

6. Logging & secrets

Never log full request bodies. Never log values for keys in SECRET_KEYS (server/lib/env-config.mjs). Verify activity-log redaction still applies.

7. Route conventions

GET/POST/PUT/DELETE /api/<resource> plus GET /api/stream/<verb> for SSE.
Buffered script runners go in the table inside createApp(), not as ad-hoc handlers.

8. Tests

Every new route needs a test in tests/*.test.mjs. Use createApp() in-process, not the running server.
Tests must bootstrap fixtures via CAREER_OPS_ROOT=$(mktemp -d) when the parent layout is needed.

Read the full file on GitHub · 51 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 51 lines · 89 tokens per session scan A dab523fd4778

Subscribe to this mod's changes

web-ui-route-reviewer is an agent published in the GitHub repository Fighter90/career-ops-ui (64 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 755 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Backend and APIs Claude Code Code review ashby career-ops express greenhouse-api hh-ru

career-ops-ui: Agent for Claude Code